Make strtolower() and strtoupper() do ASCII case conversion (#7506)

Implement RFC https://wiki.php.net/rfc/strtolower-ascii

UPGRADING

@@ -19,6 +19,14 @@ PHP 8.2 UPGRADE NOTES
 1. Backward Incompatible Changes
 ========================================
 
+- Standard:
+  . strtolower() and strtoupper() are no longer locale-sensitive. They now
+    perform ASCII case conversion, as if the locale were "C". Use
+    mb_strtolower() if you want localized case conversion. Similarly, stristr,
+    stripos, strripos, lcfirst, ucfirst, ucwords, str_ireplace,
+    array_change_key_case and sorting with SORT_FLAG_CASE use ASCII case
+    conversion.
+
 ========================================
 2. New Features
 ========================================

Zend/tests/lc_ctype_inheritance.phpt

@@ -9,17 +9,30 @@ LC_CTYPE=de_DE
 --FILE--
 <?php
 
-var_dump(setlocale(LC_CTYPE, "0"));
+echo "inherited\n";
-var_dump(bin2hex(strtoupper("\xe4")));
+echo 'ctype_lower(\xe4): ' . (ctype_lower("\xe4") ? 'y' : 'n') . "\n";
+echo 'preg_match(\w, \xe4): ';
 var_dump(preg_match('/\w/', "\xe4"));
+
+var_dump(setlocale(LC_CTYPE, "0"));
+echo 'ctype_lower(\xe4): ' . (ctype_lower("\xe4") ? 'y' : 'n') . "\n";
+echo 'preg_match(\w, \xe4): ';
+var_dump(preg_match('/\w/', "\xe4"));
+
+echo "de_DE\n";
 var_dump(setlocale(LC_CTYPE, "de_DE", "de-DE") !== false);
-var_dump(bin2hex(strtoupper("\xe4")));
+echo 'ctype_lower(\xe4): ' . (ctype_lower("\xe4") ? 'y' : 'n') . "\n";
+echo 'preg_match(\w, \xe4): ';
 var_dump(preg_match('/\w/', "\xe4"));
 ?>
 --EXPECTF--
+inherited
+ctype_lower(\xe4): n
+preg_match(\w, \xe4): int(0)
 string(%d) "C%r(\.UTF-8)?%r"
-string(2) "e4"
+ctype_lower(\xe4): n
-int(0)
+preg_match(\w, \xe4): int(0)
+de_DE
 bool(true)
-string(2) "c4"
+ctype_lower(\xe4): y
-int(1)
+preg_match(\w, \xe4): int(1)

Zend/zend_operators.c

@@ -126,9 +126,9 @@ ZEND_API const unsigned char zend_toupper_map[256] = {
  * Functions using locale lowercase:
  	 	zend_binary_strncasecmp_l
  	 	zend_binary_strcasecmp_l
+ * Functions using ascii lowercase:
 		string_compare_function_ex
 		string_case_compare_function
- * Functions using ascii lowercase:
   		zend_str_tolower_copy
 		zend_str_tolower_dup
 		zend_str_tolower
@@ -1997,7 +1997,7 @@ ZEND_API int ZEND_FASTCALL string_compare_function_ex(zval *op1, zval *op2, bool
 	int ret;
 
 	if (case_insensitive) {
-		ret = zend_binary_strcasecmp_l(ZSTR_VAL(str1), ZSTR_LEN(str1), ZSTR_VAL(str2), ZSTR_LEN(str1));
+		ret = zend_binary_strcasecmp(ZSTR_VAL(str1), ZSTR_LEN(str1), ZSTR_VAL(str2), ZSTR_LEN(str1));
 	} else {
 		ret = zend_binary_strcmp(ZSTR_VAL(str1), ZSTR_LEN(str1), ZSTR_VAL(str2), ZSTR_LEN(str2));
 	}
@@ -2037,13 +2037,13 @@ ZEND_API int ZEND_FASTCALL string_case_compare_function(zval *op1, zval *op2) /*
 		if (Z_STR_P(op1) == Z_STR_P(op2)) {
 			return 0;
 		} else {
-			return zend_binary_strcasecmp_l(Z_STRVAL_P(op1), Z_STRLEN_P(op1), Z_STRVAL_P(op2), Z_STRLEN_P(op2));
+			return zend_binary_strcasecmp(Z_STRVAL_P(op1), Z_STRLEN_P(op1), Z_STRVAL_P(op2), Z_STRLEN_P(op2));
 		}
 	} else {
 		zend_string *tmp_str1, *tmp_str2;
 		zend_string *str1 = zval_get_tmp_string(op1, &tmp_str1);
 		zend_string *str2 = zval_get_tmp_string(op2, &tmp_str2);
-		int ret = zend_binary_strcasecmp_l(ZSTR_VAL(str1), ZSTR_LEN(str1), ZSTR_VAL(str2), ZSTR_LEN(str1));
+		int ret = zend_binary_strcasecmp(ZSTR_VAL(str1), ZSTR_LEN(str1), ZSTR_VAL(str2), ZSTR_LEN(str1));
 
 		zend_tmp_string_release(tmp_str1);
 		zend_tmp_string_release(tmp_str2);

ext/pdo_dblib/dblib_stmt.c

@@ -21,7 +21,6 @@
 
 #include "php.h"
 #include "php_ini.h"
-#include "ext/standard/php_string.h"
 #include "ext/standard/info.h"
 #include "pdo/php_pdo.h"
 #include "pdo/php_pdo_driver.h"

ext/standard/string.c

@@ -1346,16 +1346,7 @@ return_false:
 /* {{{ php_strtoupper */
 PHPAPI char *php_strtoupper(char *s, size_t len)
 {
-	unsigned char *c;
+	zend_str_toupper(s, len);
-	const unsigned char *e;
-
-	c = (unsigned char *)s;
-	e = (unsigned char *)c+len;
-
-	while (c < e) {
-		*c = toupper(*c);
-		c++;
-	}
 	return s;
 }
 /* }}} */
@@ -1363,35 +1354,7 @@ PHPAPI char *php_strtoupper(char *s, size_t len)
 /* {{{ php_string_toupper */
 PHPAPI zend_string *php_string_toupper(zend_string *s)
 {
-	unsigned char *c;
+	return zend_string_toupper(s);
-	const unsigned char *e;
-
-	if (EXPECTED(!BG(ctype_string))) {
-		return zend_string_toupper(s);
-	}
-	c = (unsigned char *)ZSTR_VAL(s);
-	e = c + ZSTR_LEN(s);
-
-	while (c < e) {
-		if (islower(*c)) {
-			unsigned char *r;
-			zend_string *res = zend_string_alloc(ZSTR_LEN(s), 0);
-
-			if (c != (unsigned char*)ZSTR_VAL(s)) {
-				memcpy(ZSTR_VAL(res), ZSTR_VAL(s), c - (unsigned char*)ZSTR_VAL(s));
-			}
-			r = c + (ZSTR_VAL(res) - ZSTR_VAL(s));
-			while (c < e) {
-				*r = toupper(*c);
-				r++;
-				c++;
-			}
-			*r = '\0';
-			return res;
-		}
-		c++;
-	}
-	return zend_string_copy(s);
 }
 /* }}} */
 
@@ -1404,23 +1367,14 @@ PHP_FUNCTION(strtoupper)
 		Z_PARAM_STR(arg)
 	ZEND_PARSE_PARAMETERS_END();
 
-	RETURN_STR(php_string_toupper(arg));
+	RETURN_STR(zend_string_toupper(arg));
 }
 /* }}} */
 
 /* {{{ php_strtolower */
 PHPAPI char *php_strtolower(char *s, size_t len)
 {
-	unsigned char *c;
+	zend_str_tolower(s, len);
-	const unsigned char *e;
-
-	c = (unsigned char *)s;
-	e = c+len;
-
-	while (c < e) {
-		*c = tolower(*c);
-		c++;
-	}
 	return s;
 }
 /* }}} */
@@ -1428,32 +1382,7 @@ PHPAPI char *php_strtolower(char *s, size_t len)
 /* {{{ php_string_tolower */
 PHPAPI zend_string *php_string_tolower(zend_string *s)
 {
-	if (EXPECTED(!BG(ctype_string))) {
+	return zend_string_tolower(s);
-		return zend_string_tolower(s);
-	}
-
-	unsigned char *c = (unsigned char *)ZSTR_VAL(s);
-	const unsigned char *e = c + ZSTR_LEN(s);
-	while (c < e) {
-		if (isupper(*c)) {
-			unsigned char *r;
-			zend_string *res = zend_string_alloc(ZSTR_LEN(s), 0);
-
-			if (c != (unsigned char*)ZSTR_VAL(s)) {
-				memcpy(ZSTR_VAL(res), ZSTR_VAL(s), c - (unsigned char*)ZSTR_VAL(s));
-			}
-			r = c + (ZSTR_VAL(res) - ZSTR_VAL(s));
-			while (c < e) {
-				*r = tolower(*c);
-				r++;
-				c++;
-			}
-			*r = '\0';
-			return res;
-		}
-		c++;
-	}
-	return zend_string_copy(s);
 }
 /* }}} */
 
@@ -1466,7 +1395,7 @@ PHP_FUNCTION(strtolower)
 		Z_PARAM_STR(str)
 	ZEND_PARSE_PARAMETERS_END();
 
-	RETURN_STR(php_string_tolower(str));
+	RETURN_STR(zend_string_tolower(str));
 }
 /* }}} */
 
@@ -1758,8 +1687,8 @@ PHP_FUNCTION(pathinfo)
    case insensitive strstr */
 PHPAPI char *php_stristr(char *s, char *t, size_t s_len, size_t t_len)
 {
-	php_strtolower(s, s_len);
+	zend_str_tolower(s, s_len);
-	php_strtolower(t, t_len);
+	zend_str_tolower(t, t_len);
 	return (char*)php_memnstr(s, t, t_len, s + s_len);
 }
 /* }}} */
@@ -1982,8 +1911,8 @@ PHP_FUNCTION(stripos)
 		RETURN_FALSE;
 	}
 
-	haystack_dup = php_string_tolower(haystack);
+	haystack_dup = zend_string_tolower(haystack);
-	needle_dup = php_string_tolower(needle);
+	needle_dup = zend_string_tolower(needle);
 	found = (char*)php_memnstr(ZSTR_VAL(haystack_dup) + offset,
 			ZSTR_VAL(needle_dup), ZSTR_LEN(needle_dup), ZSTR_VAL(haystack_dup) + ZSTR_LEN(haystack));
 
@@ -2077,10 +2006,9 @@ PHP_FUNCTION(strripos)
 			}
 			e = ZSTR_VAL(haystack) + (ZSTR_LEN(haystack) + (size_t)offset);
 		}
-		/* Borrow that ord_needle buffer to avoid repeatedly tolower()ing needle */
+		lowered = zend_tolower_ascii(*ZSTR_VAL(needle));
-		lowered = tolower(*ZSTR_VAL(needle));
 		while (e >= p) {
-			if (tolower(*e) == lowered) {
+			if (zend_tolower_ascii(*e) == lowered) {
 				RETURN_LONG(e - p + (offset > 0 ? offset : 0));
 			}
 			e--;
@@ -2088,7 +2016,7 @@ PHP_FUNCTION(strripos)
 		RETURN_FALSE;
 	}
 
-	haystack_dup = php_string_tolower(haystack);
+	haystack_dup = zend_string_tolower(haystack);
 	if (offset >= 0) {
 		if ((size_t)offset > ZSTR_LEN(haystack)) {
 			zend_string_release_ex(haystack_dup, 0);
@@ -2112,7 +2040,7 @@ PHP_FUNCTION(strripos)
 		}
 	}
 
-	needle_dup = php_string_tolower(needle);
+	needle_dup = zend_string_tolower(needle);
 	if ((found = (char *)zend_memnrstr(p, ZSTR_VAL(needle_dup), ZSTR_LEN(needle_dup), e))) {
 		RETVAL_LONG(found - ZSTR_VAL(haystack_dup));
 		zend_string_release_ex(needle_dup, 0);
@@ -2647,7 +2575,7 @@ PHP_FUNCTION(chr)
 static zend_string* php_ucfirst(zend_string *str)
 {
 	const unsigned char ch = ZSTR_VAL(str)[0];
-	unsigned char r = toupper(ch);
+	unsigned char r = zend_toupper_ascii(ch);
 	if (r == ch) {
 		return zend_string_copy(str);
 	} else {
@@ -2679,7 +2607,7 @@ PHP_FUNCTION(ucfirst)
    Lowercase the first character of the word in a native string */
 static zend_string* php_lcfirst(zend_string *str)
 {
-	unsigned char r = tolower(ZSTR_VAL(str)[0]);
+	unsigned char r = zend_tolower_ascii(ZSTR_VAL(str)[0]);
 	if (r == ZSTR_VAL(str)[0]) {
 		return zend_string_copy(str);
 	} else {
@@ -2732,10 +2660,10 @@ PHP_FUNCTION(ucwords)
 	ZVAL_STRINGL(return_value, ZSTR_VAL(str), ZSTR_LEN(str));
 	r = Z_STRVAL_P(return_value);
 
-	*r = toupper((unsigned char) *r);
+	*r = zend_toupper_ascii((unsigned char) *r);
 	for (r_end = r + Z_STRLEN_P(return_value) - 1; r < r_end; ) {
 		if (mask[(unsigned char)*r++]) {
-			*r = toupper((unsigned char) *r);
+			*r = zend_toupper_ascii((unsigned char) *r);
 		}
 	}
 }
@@ -3067,11 +2995,11 @@ static zend_string* php_char_to_str_ex(zend_string *str, char from, char *to, si
 	if (case_sensitivity) {
 		char_count = count_chars(ZSTR_VAL(str), ZSTR_LEN(str), from);
 	} else {
-		lc_from = tolower(from);
 		char_count = 0;
+		lc_from = zend_tolower_ascii(from);
 		source_end = ZSTR_VAL(str) + ZSTR_LEN(str);
 		for (source = ZSTR_VAL(str); source < source_end; source++) {
-			if (tolower(*source) == lc_from) {
+			if (zend_tolower_ascii(*source) == lc_from) {
 				char_count++;
 			}
 		}
@@ -3111,7 +3039,7 @@ static zend_string* php_char_to_str_ex(zend_string *str, char from, char *to, si
 	} else {
 		source_end = ZSTR_VAL(str) + ZSTR_LEN(str);
 		for (source = ZSTR_VAL(str); source < source_end; source++) {
-			if (tolower(*source) == lc_from) {
+			if (zend_tolower_ascii(*source) == lc_from) {
 				memcpy(target, to, to_len);
 				target += to_len;
 			} else {
@@ -4345,7 +4273,7 @@ static zend_long php_str_replace_in_subject(
 					zend_long old_replace_count = replace_count;
 
 					if (!lc_subject_str) {
-						lc_subject_str = php_string_tolower(subject_str);
+						lc_subject_str = zend_string_tolower(subject_str);
 					}
 					tmp_result = php_str_to_str_i_ex(subject_str, ZSTR_VAL(lc_subject_str),
 							search_str, replace_value, replace_len, &replace_count);
@@ -4398,7 +4326,7 @@ static zend_long php_str_replace_in_subject(
 						ZSTR_VAL(search_str), ZSTR_LEN(search_str),
 						ZSTR_VAL(replace_str), ZSTR_LEN(replace_str), &replace_count));
 			} else {
-				lc_subject_str = php_string_tolower(subject_str);
+				lc_subject_str = zend_string_tolower(subject_str);
 				ZVAL_STR(result, php_str_to_str_i_ex(subject_str, ZSTR_VAL(lc_subject_str),
 						search_str, ZSTR_VAL(replace_str), ZSTR_LEN(replace_str), &replace_count));
 				zend_string_release_ex(lc_subject_str, 0);
@@ -4941,7 +4869,7 @@ int php_tag_find(char *tag, size_t len, const char *set) {
 
 	n = norm;
 	t = tag;
-	c = tolower(*t);
+	c = zend_tolower_ascii(*t);
 	/*
 	   normalize the tag removing leading and trailing whitespace
 	   and turn any <a whatever...> into just <a> and any </tag>
@@ -4969,7 +4897,7 @@ int php_tag_find(char *tag, size_t len, const char *set) {
 				}
 				break;
 		}
-		c = tolower(*(++t));
+		c = zend_tolower_ascii(*(++t));
 	}
 	*(n++) = '>';
 	*n = '\0';

ext/standard/tests/strings/bug79986.phpt

@@ -1,13 +0,0 @@
---TEST--
-Bug #79986 (str_ireplace bug with diacritics characters)
---SKIPIF--
-<?php
-if (!setlocale(LC_ALL, 'de_DE.ISO-8859-1', 'de-DE')) die('skip German locale not available');
-?>
---FILE--
-<?php
-setlocale(LC_ALL, 'de_DE.ISO-8859-1', 'de-DE');
-echo str_ireplace(["\xE4", "\xF6", "\xFC"], ['1', '2', '3'], "\xE4\xC4 \xF6\xD6 \xFC\xDC") . PHP_EOL;
-?>
---EXPECT--
-11 22 33

ext/standard/tests/strings/strtolower-win32.phpt

@@ -1,340 +0,0 @@
---TEST--
-Test strtolower() function
---SKIPIF--
-<?php
-if (substr(PHP_OS, 0, 3) != "WIN" || !setlocale(LC_CTYPE, "English_United States.1252"))
-  die('skip Run only on Windows with locale "English_United States.1252" available');
-?>
---FILE--
-<?php
-setlocale(LC_CTYPE, "English_United States.1252");
-
-echo "*** Testing strtolower() with all 256 chars ***\n";
-for ($i=0; $i<=255; $i++){
-  $char = chr($i);
-  print(bin2hex($char))." => ".(bin2hex(strtolower("$char")))."\n";
-}
-
-echo "*** Testing strlower() with basic strings ***\n";
-$str = "Mary Had A liTTle LAmb and ShE loveD IT So\n";
-var_dump(strtolower($str));
-
-echo "\n*** Testing strtolower() with various strings ***";
-/* strings to pass strtolower() */
-$strings = array (
-  "",
-  "string",
-  "stRINg0234",
-  "1.233.344StrinG12333",
-  "$$$$$$!!!!@@@@@@@ ABCDEF !!!***",
-  "ABCD\0abcdABCD",
-  TRUE,
-  FALSE,
-);
-
-$count = 0;
-/* loop through to check possible variations */
-foreach ($strings as $string) {
-  echo "\n-- Iteration $count --\n";
-  var_dump( strtolower($string) );
-  $count++;
-}
-
-echo "\n*** Testing strtolower() with two different case strings ***\n";
-if (strtolower("HeLLo woRLd") === strtolower("hEllo WORLD"))
-  echo "strings are same, with Case Insensitive\n";
-else
-  echo "strings are not same\n";
-
-echo "*** Done ***";
-?>
---EXPECTF--
-*** Testing strtolower() with all 256 chars ***
-00 => 00
-01 => 01
-02 => 02
-03 => 03
-04 => 04
-05 => 05
-06 => 06
-07 => 07
-08 => 08
-09 => 09
-0a => 0a
-0b => 0b
-0c => 0c
-0d => 0d
-0e => 0e
-0f => 0f
-10 => 10
-11 => 11
-12 => 12
-13 => 13
-14 => 14
-15 => 15
-16 => 16
-17 => 17
-18 => 18
-19 => 19
-1a => 1a
-1b => 1b
-1c => 1c
-1d => 1d
-1e => 1e
-1f => 1f
-20 => 20
-21 => 21
-22 => 22
-23 => 23
-24 => 24
-25 => 25
-26 => 26
-27 => 27
-28 => 28
-29 => 29
-2a => 2a
-2b => 2b
-2c => 2c
-2d => 2d
-2e => 2e
-2f => 2f
-30 => 30
-31 => 31
-32 => 32
-33 => 33
-34 => 34
-35 => 35
-36 => 36
-37 => 37
-38 => 38
-39 => 39
-3a => 3a
-3b => 3b
-3c => 3c
-3d => 3d
-3e => 3e
-3f => 3f
-40 => 40
-41 => 61
-42 => 62
-43 => 63
-44 => 64
-45 => 65
-46 => 66
-47 => 67
-48 => 68
-49 => 69
-4a => 6a
-4b => 6b
-4c => 6c
-4d => 6d
-4e => 6e
-4f => 6f
-50 => 70
-51 => 71
-52 => 72
-53 => 73
-54 => 74
-55 => 75
-56 => 76
-57 => 77
-58 => 78
-59 => 79
-5a => 7a
-5b => 5b
-5c => 5c
-5d => 5d
-5e => 5e
-5f => 5f
-60 => 60
-61 => 61
-62 => 62
-63 => 63
-64 => 64
-65 => 65
-66 => 66
-67 => 67
-68 => 68
-69 => 69
-6a => 6a
-6b => 6b
-6c => 6c
-6d => 6d
-6e => 6e
-6f => 6f
-70 => 70
-71 => 71
-72 => 72
-73 => 73
-74 => 74
-75 => 75
-76 => 76
-77 => 77
-78 => 78
-79 => 79
-7a => 7a
-7b => 7b
-7c => 7c
-7d => 7d
-7e => 7e
-7f => 7f
-80 => 80
-81 => 81
-82 => 82
-83 => 83
-84 => 84
-85 => 85
-86 => 86
-87 => 87
-88 => 88
-89 => 89
-8a => 9a
-8b => 8b
-8c => 9c
-8d => 8d
-8e => 9e
-8f => 8f
-90 => 90
-91 => 91
-92 => 92
-93 => 93
-94 => 94
-95 => 95
-96 => 96
-97 => 97
-98 => 98
-99 => 99
-9a => 9a
-9b => 9b
-9c => 9c
-9d => 9d
-9e => 9e
-9f => ff
-a0 => a0
-a1 => a1
-a2 => a2
-a3 => a3
-a4 => a4
-a5 => a5
-a6 => a6
-a7 => a7
-a8 => a8
-a9 => a9
-aa => aa
-ab => ab
-ac => ac
-ad => ad
-ae => ae
-af => af
-b0 => b0
-b1 => b1
-b2 => b2
-b3 => b3
-b4 => b4
-b5 => b5
-b6 => b6
-b7 => b7
-b8 => b8
-b9 => b9
-ba => ba
-bb => bb
-bc => bc
-bd => bd
-be => be
-bf => bf
-c0 => e0
-c1 => e1
-c2 => e2
-c3 => e3
-c4 => e4
-c5 => e5
-c6 => e6
-c7 => e7
-c8 => e8
-c9 => e9
-ca => ea
-cb => eb
-cc => ec
-cd => ed
-ce => ee
-cf => ef
-d0 => f0
-d1 => f1
-d2 => f2
-d3 => f3
-d4 => f4
-d5 => f5
-d6 => f6
-d7 => d7
-d8 => f8
-d9 => f9
-da => fa
-db => fb
-dc => fc
-dd => fd
-de => fe
-df => df
-e0 => e0
-e1 => e1
-e2 => e2
-e3 => e3
-e4 => e4
-e5 => e5
-e6 => e6
-e7 => e7
-e8 => e8
-e9 => e9
-ea => ea
-eb => eb
-ec => ec
-ed => ed
-ee => ee
-ef => ef
-f0 => f0
-f1 => f1
-f2 => f2
-f3 => f3
-f4 => f4
-f5 => f5
-f6 => f6
-f7 => f7
-f8 => f8
-f9 => f9
-fa => fa
-fb => fb
-fc => fc
-fd => fd
-fe => fe
-ff => ff
-*** Testing strlower() with basic strings ***
-string(43) "mary had a little lamb and she loved it so
-"
-
-*** Testing strtolower() with various strings ***
--- Iteration 0 --
-string(0) ""
-
--- Iteration 1 --
-string(6) "string"
-
--- Iteration 2 --
-string(10) "string0234"
-
--- Iteration 3 --
-string(20) "1.233.344string12333"
-
--- Iteration 4 --
-string(31) "$$$$$$!!!!@@@@@@@ abcdef !!!***"
-
--- Iteration 5 --
-string(13) "abcd%0abcdabcd"
-
--- Iteration 6 --
-string(1) "1"
-
--- Iteration 7 --
-string(0) ""
-
-*** Testing strtolower() with two different case strings ***
-strings are same, with Case Insensitive
-*** Done ***

ext/standard/tests/strings/strtolower.phpt

@@ -1,27 +1,10 @@
 --TEST--
 Test strtolower() function
---SKIPIF--
-<?php
-if( substr(PHP_OS, 0, 3) == 'WIN') {
-  if (!setlocale(LC_ALL, 'C')) {
-    die('skip need "C" locale (this windows is broken)');
-  }
-} else {
-  if (!setlocale(LC_ALL, 'en_US.UTF-8', 'en')) {
-    die('skip need "en_US.UTF-8" locale');
-  }
-}
-?>
 --FILE--
 <?php
-if( substr(PHP_OS, 0, 3) == 'WIN') {
-  setlocale(LC_ALL, 'C');
-} else {
-  setlocale(LC_ALL, 'en_US.UTF-8');
-}
 
-echo "*** Testing strtolower() with 128 chars ***\n";
+echo "*** Testing strtolower() with 256 chars ***\n";
-for ($i=0; $i<=127; $i++){
+for ($i=0; $i<=255; $i++){
   $char = chr($i);
   print(bin2hex($char))." => ".(bin2hex(strtolower("$char")))."\n";
 }
@@ -66,7 +49,7 @@ else
 echo "*** Done ***";
 ?>
 --EXPECTF--
-*** Testing strtolower() with 128 chars ***
+*** Testing strtolower() with 256 chars ***
 00 => 00
 01 => 01
 02 => 02
@@ -195,6 +178,134 @@ echo "*** Done ***";
 7d => 7d
 7e => 7e
 7f => 7f
+80 => 80
+81 => 81
+82 => 82
+83 => 83
+84 => 84
+85 => 85
+86 => 86
+87 => 87
+88 => 88
+89 => 89
+8a => 8a
+8b => 8b
+8c => 8c
+8d => 8d
+8e => 8e
+8f => 8f
+90 => 90
+91 => 91
+92 => 92
+93 => 93
+94 => 94
+95 => 95
+96 => 96
+97 => 97
+98 => 98
+99 => 99
+9a => 9a
+9b => 9b
+9c => 9c
+9d => 9d
+9e => 9e
+9f => 9f
+a0 => a0
+a1 => a1
+a2 => a2
+a3 => a3
+a4 => a4
+a5 => a5
+a6 => a6
+a7 => a7
+a8 => a8
+a9 => a9
+aa => aa
+ab => ab
+ac => ac
+ad => ad
+ae => ae
+af => af
+b0 => b0
+b1 => b1
+b2 => b2
+b3 => b3
+b4 => b4
+b5 => b5
+b6 => b6
+b7 => b7
+b8 => b8
+b9 => b9
+ba => ba
+bb => bb
+bc => bc
+bd => bd
+be => be
+bf => bf
+c0 => c0
+c1 => c1
+c2 => c2
+c3 => c3
+c4 => c4
+c5 => c5
+c6 => c6
+c7 => c7
+c8 => c8
+c9 => c9
+ca => ca
+cb => cb
+cc => cc
+cd => cd
+ce => ce
+cf => cf
+d0 => d0
+d1 => d1
+d2 => d2
+d3 => d3
+d4 => d4
+d5 => d5
+d6 => d6
+d7 => d7
+d8 => d8
+d9 => d9
+da => da
+db => db
+dc => dc
+dd => dd
+de => de
+df => df
+e0 => e0
+e1 => e1
+e2 => e2
+e3 => e3
+e4 => e4
+e5 => e5
+e6 => e6
+e7 => e7
+e8 => e8
+e9 => e9
+ea => ea
+eb => eb
+ec => ec
+ed => ed
+ee => ee
+ef => ef
+f0 => f0
+f1 => f1
+f2 => f2
+f3 => f3
+f4 => f4
+f5 => f5
+f6 => f6
+f7 => f7
+f8 => f8
+f9 => f9
+fa => fa
+fb => fb
+fc => fc
+fd => fd
+fe => fe
+ff => ff
 *** Testing strlower() with basic strings ***
 string(43) "mary had a little lamb and she loved it so
 "

ext/standard/tests/strings/strtoupper.phpt

@@ -1,20 +0,0 @@
---TEST--
-Test strtoupper on non-ASCII characters
---SKIPIF--
-<?php
-if (!setlocale(LC_CTYPE, "de_DE", "de", "german", "ge", "de_DE.ISO8859-1", "ISO8859-1")) {
-        die("skip locale needed for this test is not supported on this platform");
-}
-?>
---FILE--
-<?php
-$chars = "äöü";
-// Not sure which is most portable. BSD's answer to
-// this one. A small array based on PHP_OS should
-// cover a majority of systems and makes the problem
-// of locales transparent for the end user.
-setlocale(LC_CTYPE, "de_DE", "de", "german", "ge", "de_DE.ISO8859-1", "ISO8859-1");
-echo strtoupper($chars)."\n";
-?>
---EXPECT--
-ÄÖÜ

ext/standard/tests/strings/strtoupper1-win32.phpt

@@ -1,342 +0,0 @@
---TEST--
-Test strtoupper() function
---SKIPIF--
-<?php
-if (substr(PHP_OS, 0, 3) != "WIN" || !setlocale(LC_CTYPE, "English_United States.1252"))
-  die('skip Run only on Windows with locale "English_United States.1252" available');
-?>
---FILE--
-<?php
-
-setlocale(LC_CTYPE, "English_United States.1252");
-
-echo "*** Testing strtoupper() with all 256 chars ***\n";
-for ($i=0; $i<=255; $i++){
-  $char = chr($i);
-  print(bin2hex($char))." => ".(bin2hex(strtoupper("$char")))."\n";
-}
-
-echo "\n*** Testing strtoupper() with basic strings ***\n";
-$str = "Mary Had A liTTle LAmb and ShE loveD IT So\n";
-var_dump(strtoupper($str));
-
-echo "\n*** Testing strtoupper() with various strings ***";
-/* strings to pass strtoupper() */
-$strings = array (
-  "",
-  "string",
-  "stRINg0234",
-  "1.233.344StrinG12333",
-  "$$$$$$!!!!@@@@@@@ ABCDEF !!!***",
-  "ABCD\0abcdABCD",
-  TRUE,
-  FALSE,
-);
-
-$count = 0;
-/* loop through to check possible variations */
-foreach ($strings as $string) {
-  echo "\n-- Iteration $count --\n";
-  var_dump( strtoupper($string) );
-  $count++;
-}
-
-echo "\n*** Testing strtoupper() with two different case strings ***\n";
-if (strtoupper("HeLLo woRLd") === strtoupper("hEllo WORLD"))
-  echo "strings are same, with Case Insensitive\n";
-else
-  echo "strings are not same\n";
-
-echo "*** Done ***";
-?>
---EXPECTF--
-*** Testing strtoupper() with all 256 chars ***
-00 => 00
-01 => 01
-02 => 02
-03 => 03
-04 => 04
-05 => 05
-06 => 06
-07 => 07
-08 => 08
-09 => 09
-0a => 0a
-0b => 0b
-0c => 0c
-0d => 0d
-0e => 0e
-0f => 0f
-10 => 10
-11 => 11
-12 => 12
-13 => 13
-14 => 14
-15 => 15
-16 => 16
-17 => 17
-18 => 18
-19 => 19
-1a => 1a
-1b => 1b
-1c => 1c
-1d => 1d
-1e => 1e
-1f => 1f
-20 => 20
-21 => 21
-22 => 22
-23 => 23
-24 => 24
-25 => 25
-26 => 26
-27 => 27
-28 => 28
-29 => 29
-2a => 2a
-2b => 2b
-2c => 2c
-2d => 2d
-2e => 2e
-2f => 2f
-30 => 30
-31 => 31
-32 => 32
-33 => 33
-34 => 34
-35 => 35
-36 => 36
-37 => 37
-38 => 38
-39 => 39
-3a => 3a
-3b => 3b
-3c => 3c
-3d => 3d
-3e => 3e
-3f => 3f
-40 => 40
-41 => 41
-42 => 42
-43 => 43
-44 => 44
-45 => 45
-46 => 46
-47 => 47
-48 => 48
-49 => 49
-4a => 4a
-4b => 4b
-4c => 4c
-4d => 4d
-4e => 4e
-4f => 4f
-50 => 50
-51 => 51
-52 => 52
-53 => 53
-54 => 54
-55 => 55
-56 => 56
-57 => 57
-58 => 58
-59 => 59
-5a => 5a
-5b => 5b
-5c => 5c
-5d => 5d
-5e => 5e
-5f => 5f
-60 => 60
-61 => 41
-62 => 42
-63 => 43
-64 => 44
-65 => 45
-66 => 46
-67 => 47
-68 => 48
-69 => 49
-6a => 4a
-6b => 4b
-6c => 4c
-6d => 4d
-6e => 4e
-6f => 4f
-70 => 50
-71 => 51
-72 => 52
-73 => 53
-74 => 54
-75 => 55
-76 => 56
-77 => 57
-78 => 58
-79 => 59
-7a => 5a
-7b => 7b
-7c => 7c
-7d => 7d
-7e => 7e
-7f => 7f
-80 => 80
-81 => 81
-82 => 82
-83 => 83
-84 => 84
-85 => 85
-86 => 86
-87 => 87
-88 => 88
-89 => 89
-8a => 8a
-8b => 8b
-8c => 8c
-8d => 8d
-8e => 8e
-8f => 8f
-90 => 90
-91 => 91
-92 => 92
-93 => 93
-94 => 94
-95 => 95
-96 => 96
-97 => 97
-98 => 98
-99 => 99
-9a => 8a
-9b => 9b
-9c => 8c
-9d => 9d
-9e => 8e
-9f => 9f
-a0 => a0
-a1 => a1
-a2 => a2
-a3 => a3
-a4 => a4
-a5 => a5
-a6 => a6
-a7 => a7
-a8 => a8
-a9 => a9
-aa => aa
-ab => ab
-ac => ac
-ad => ad
-ae => ae
-af => af
-b0 => b0
-b1 => b1
-b2 => b2
-b3 => b3
-b4 => b4
-b5 => b5
-b6 => b6
-b7 => b7
-b8 => b8
-b9 => b9
-ba => ba
-bb => bb
-bc => bc
-bd => bd
-be => be
-bf => bf
-c0 => c0
-c1 => c1
-c2 => c2
-c3 => c3
-c4 => c4
-c5 => c5
-c6 => c6
-c7 => c7
-c8 => c8
-c9 => c9
-ca => ca
-cb => cb
-cc => cc
-cd => cd
-ce => ce
-cf => cf
-d0 => d0
-d1 => d1
-d2 => d2
-d3 => d3
-d4 => d4
-d5 => d5
-d6 => d6
-d7 => d7
-d8 => d8
-d9 => d9
-da => da
-db => db
-dc => dc
-dd => dd
-de => de
-df => df
-e0 => c0
-e1 => c1
-e2 => c2
-e3 => c3
-e4 => c4
-e5 => c5
-e6 => c6
-e7 => c7
-e8 => c8
-e9 => c9
-ea => ca
-eb => cb
-ec => cc
-ed => cd
-ee => ce
-ef => cf
-f0 => d0
-f1 => d1
-f2 => d2
-f3 => d3
-f4 => d4
-f5 => d5
-f6 => d6
-f7 => f7
-f8 => d8
-f9 => d9
-fa => da
-fb => db
-fc => dc
-fd => dd
-fe => de
-ff => 9f
-
-*** Testing strtoupper() with basic strings ***
-string(43) "MARY HAD A LITTLE LAMB AND SHE LOVED IT SO
-"
-
-*** Testing strtoupper() with various strings ***
--- Iteration 0 --
-string(0) ""
-
--- Iteration 1 --
-string(6) "STRING"
-
--- Iteration 2 --
-string(10) "STRING0234"
-
--- Iteration 3 --
-string(20) "1.233.344STRING12333"
-
--- Iteration 4 --
-string(31) "$$$$$$!!!!@@@@@@@ ABCDEF !!!***"
-
--- Iteration 5 --
-string(13) "ABCD%0ABCDABCD"
-
--- Iteration 6 --
-string(1) "1"
-
--- Iteration 7 --
-string(0) ""
-
-*** Testing strtoupper() with two different case strings ***
-strings are same, with Case Insensitive
-*** Done ***

ext/standard/tests/strings/strtoupper1.phpt

@@ -1,27 +1,9 @@
 --TEST--
 Test strtoupper() function
---SKIPIF--
-<?php
-if( substr(PHP_OS, 0, 3) == 'WIN') {
-  if (!setlocale(LC_ALL, 'C')) {
-    die('skip need "C" locale (this windows is broken)');
-  }
-} else {
-  if (!setlocale(LC_ALL, 'en_US.UTF-8', 'en')) {
-    die('skip need "en_US.UTF-8" locale');
-  }
-}
-?>
 --FILE--
 <?php
-if( substr(PHP_OS, 0, 3) == 'WIN') {
+echo "*** Testing strtoupper() with 256 chars ***\n";
-  setlocale(LC_ALL, 'C');
+for ($i=0; $i<=255; $i++){
-} else {
-  setlocale(LC_ALL, 'en_US.UTF-8');
-}
-
-echo "*** Testing strtoupper() with 128 chars ***\n";
-for ($i=0; $i<=127; $i++){
   $char = chr($i);
   print(bin2hex($char))." => ".(bin2hex(strtoupper("$char")))."\n";
 }
@@ -65,7 +47,7 @@ else
 echo "*** Done ***";
 ?>
 --EXPECTF--
-*** Testing strtoupper() with 128 chars ***
+*** Testing strtoupper() with 256 chars ***
 00 => 00
 01 => 01
 02 => 02
@@ -194,6 +176,134 @@ echo "*** Done ***";
 7d => 7d
 7e => 7e
 7f => 7f
+80 => 80
+81 => 81
+82 => 82
+83 => 83
+84 => 84
+85 => 85
+86 => 86
+87 => 87
+88 => 88
+89 => 89
+8a => 8a
+8b => 8b
+8c => 8c
+8d => 8d
+8e => 8e
+8f => 8f
+90 => 90
+91 => 91
+92 => 92
+93 => 93
+94 => 94
+95 => 95
+96 => 96
+97 => 97
+98 => 98
+99 => 99
+9a => 9a
+9b => 9b
+9c => 9c
+9d => 9d
+9e => 9e
+9f => 9f
+a0 => a0
+a1 => a1
+a2 => a2
+a3 => a3
+a4 => a4
+a5 => a5
+a6 => a6
+a7 => a7
+a8 => a8
+a9 => a9
+aa => aa
+ab => ab
+ac => ac
+ad => ad
+ae => ae
+af => af
+b0 => b0
+b1 => b1
+b2 => b2
+b3 => b3
+b4 => b4
+b5 => b5
+b6 => b6
+b7 => b7
+b8 => b8
+b9 => b9
+ba => ba
+bb => bb
+bc => bc
+bd => bd
+be => be
+bf => bf
+c0 => c0
+c1 => c1
+c2 => c2
+c3 => c3
+c4 => c4
+c5 => c5
+c6 => c6
+c7 => c7
+c8 => c8
+c9 => c9
+ca => ca
+cb => cb
+cc => cc
+cd => cd
+ce => ce
+cf => cf
+d0 => d0
+d1 => d1
+d2 => d2
+d3 => d3
+d4 => d4
+d5 => d5
+d6 => d6
+d7 => d7
+d8 => d8
+d9 => d9
+da => da
+db => db
+dc => dc
+dd => dd
+de => de
+df => df
+e0 => e0
+e1 => e1
+e2 => e2
+e3 => e3
+e4 => e4
+e5 => e5
+e6 => e6
+e7 => e7
+e8 => e8
+e9 => e9
+ea => ea
+eb => eb
+ec => ec
+ed => ed
+ee => ee
+ef => ef
+f0 => f0
+f1 => f1
+f2 => f2
+f3 => f3
+f4 => f4
+f5 => f5
+f6 => f6
+f7 => f7
+f8 => f8
+f9 => f9
+fa => fa
+fb => fb
+fc => fc
+fd => fd
+fe => fe
+ff => ff
 
 *** Testing strtoupper() with basic strings ***
 string(43) "MARY HAD A LITTLE LAMB AND SHE LOVED IT SO

ext/xml/xml.c

@@ -23,7 +23,6 @@
 #include "php.h"
 
 #include "zend_variables.h"
-#include "ext/standard/php_string.h"
 #include "ext/standard/info.h"
 #include "ext/standard/html.h"